SOTAVerified

Image Generation

Image Generation (synthesis) is the task of generating new images from an existing dataset.

  • Unconditional generation refers to generating samples unconditionally from the dataset, i.e. $p(y)$
  • Conditional image generation (subtask) refers to generating samples conditionally from the dataset, based on a label, i.e. $p(y|x)$.

In this section, you can find state-of-the-art leaderboards for unconditional generation. For conditional generation, and other types of image generations, refer to the subtasks.

( Image credit: StyleGAN )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 6001–6050 of 6689 papers

TitleStatusHype
FaceForensics++: Learning to Detect Manipulated Facial ImagesCode0
FiNet: Compatible and Diverse Fashion Image Inpainting—0
Unsupervised Generative 3D Shape Learning from Natural Images—0
DSRGAN: Explicitly Learning Disentangled Representation of Underlying Structure and Rendering for Image Generation without Tuple Supervision—0
Understanding and Stabilizing GANs' Training Dynamics with Control TheoryCode0
RGBD-GAN: Unsupervised 3D Representation Learning From Natural Image Datasets via RGBD Image SynthesisCode0
Conditional Invertible Neural Networks for Guided Image Generation—0
Is There Mode Collapse? A Case Study on Face Generation and Its Black-box Calibration—0
Style-based Encoder Pre-training for Multi-modal Image Synthesis—0
BRIDGING ADVERSARIAL SAMPLES AND ADVERSARIAL NETWORKS—0
Towards Controllable and Interpretable Face Completion via Structure-Aware and Frequency-Oriented Attentive GANs—0
EINS: Long Short-Term Memory with Extrapolated Input Network Simplification—0
RPGAN: random paths as a latent space for GAN interpretabilityCode0
InfoCNF: Efficient Conditional Continuous Normalizing Flow Using Adaptive Solvers—0
Relative Pixel Prediction For Autoregressive Image Generation—0
Semantic Hierarchy Emerges in the Deep Generative Representations for Scene Synthesis—0
Exploring Cellular Protein Localization Through Semantic Image Synthesis—0
mustGAN: Multi-Stream Generative Adversarial Networks for MR Image Synthesis—0
Stochastic Conditional Generative Networks with Basis Decomposition—0
Conditional Transferring Features: Scaling GANs to Thousands of Classes with 30% Less High-quality Data for Training—0
Intelligent image synthesis to attack a segmentation CNN using adversarial learning—0
Subsampling Generative Adversarial Networks: Density Ratio Estimation in Feature Space with Softplus LossCode0
Distortion Estimation Through Explicit Modeling of the Refractive Surface—0
Synthetic dataset generation for object-to-model deep learning in industrial applicationsCode0
Human Synthesis and Scene Compositing—0
Variational Conditional GAN for Fine-grained Controllable Image Generation—0
Fourier-CPPNs for Image Synthesis—0
Synthetic CT Generation from MRI Using Improved DualGAN—0
Triplet-Aware Scene Graph Embeddings—0
Unsupervised Sketch-to-Photo SynthesisCode1
A Characteristic Function Approach to Deep Implicit Generative ModelingCode1
Controllable Text-to-Image GenerationCode0
Coupling Rendering and Generative Adversarial Networks for Artificial SAS Image Generation—0
ρ-VAE: Autoregressive parametrization of the VAE encoderCode0
FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Faces—0
Inducing Hierarchical Compositional Model by Sparsifying Generator Network—0
Learning Priors for Adversarial Autoencoders—0
Towards Learning a Self-inverse Network for Bidirectional Image-to-image Translation—0
One-to-one Mapping for Unpaired Image-to-image Translation—0
An Acceleration Framework for High Resolution Image Synthesis—0
TorchGAN: A Flexible Framework for GAN Training and EvaluationCode0
Testing Deep Learning Models for Image Analysis Using Object-Relevant Metamorphic Relations—0
Relationship-Aware Spatial Perception Fusion for Realistic Scene Layout Generation—0
BooVAE: Boosting Approach for Continual Learning of VAECode0
Systematic Analysis of Image Generation using GANs—0
Flexible Conditional Image Generation of Missing Data with Learned Mental Maps—0
EEG Signal Dimensionality Reduction and Classification using Tensor Decomposition and Deep Convolutional Neural Networks—0
PixelVAE++: Improved PixelVAE with Discrete Prior—0
Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry—0
DUAL-GLOW: Conditional Flow-Based Generative Model for Modality TransferCode0
Show:102550
← PrevPage 121 of 134Next →
All datasetsImageNet 256x256CIFAR-10ImageNet 64x64ImageNet 512x512FFHQ 256 x 256CelebA 64x64ImageNet 32x32LSUN Bedroom 256 x 256STL-10LSUN Churches 256 x 256ImageNet 128x128FFHQ 1024 x 1024

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Improved DDPMFID12.3—Unverified
2ADMFID11.84—Unverified
3BigGAN-deepFID8.1—Unverified
4Polarity-BigGANFID6.82—Unverified
5VQGAN+Transformer (k=mixed, p=1.0, a=0.005)FID6.59—Unverified
6MaskGITFID6.18—Unverified
7VQGAN+Transformer (k=600, p=1.0, a=0.05)FID5.2—Unverified
8CDMFID4.88—Unverified
9ADM-GFID4.59—Unverified
10RINFID4.51—Unverified
#ModelMetricClaimedVerifiedStatus
1PresGANFID52.2—Unverified
2RESFLOWFID48.29—Unverified
3Residual FlowFID46.37—Unverified
4GLF+perceptual loss (ours)FID44.6—Unverified
5ProdPoly no activation functionsFID40.45—Unverified
6ProdPoly no activation functionsFID36.77—Unverified
7ACGANFID35.47—Unverified
8DenseFlow-74-10FID34.9—Unverified
9NVAE w/ flowFID32.53—Unverified
10QSNGANFID31.97—Unverified
#ModelMetricClaimedVerifiedStatus
1GLIDE + CLSFID30.87—Unverified
2GLIDE + CLIPFID30.46—Unverified
3GLIDE + CLS-FREEFID29.22—Unverified
4GLIDE + CLIP + CLS + CLS-FREEFID29.18—Unverified
5PGMGANFID21.73—Unverified
6CLR-GANFID20.27—Unverified
7FMFID14.45—Unverified
8CT (Direct Generation, NFE=1)FID13—Unverified
9CT (Direct Generation, NFE=2)FID11.1—Unverified
10GLIDE +CLSKID7.95—Unverified